SOTAVerified

Open Set Learning

Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. Open set learning (OSL) is a more challenging and realistic setting, where there exist test samples from the classes that are unseen during training. Open set recognition (OSR) is the sub-task of detecting test samples which do not come from the training.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–267 of 267 papers

TitleStatusHype
Disentangled representations of microscopy imagesCode0
Open-Set Face Recognition with Maximal Entropy and Objectosphere LossCode0
Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature AugmentationCode0
ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence AlignmentCode0
An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic EnvironmentsCode0
Dense open-set recognition with synthetic outliers generated by Real NVPCode0
Simple Domain Generalization Methods are Strong Baselines for Open Domain GeneralizationCode0
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set RecognitionCode0
Classification-Reconstruction Learning for Open-Set RecognitionCode0
Deep Learning for Leopard Individual Identification: An Adaptive Angular Margin ApproachCode0
Open-set Recognition based on the Combination of Deep Learning and Ensemble Method for Detecting Unknown Traffic ScenariosCode0
Contracting Skeletal Kinematics for Human-Related Video Anomaly DetectionCode0
Open-Set Recognition in the Age of Vision-Language ModelsCode0
Sparse Representation-based Open Set RecognitionCode0
A Survey of Text Classification Under Class Distribution ShiftCode0
Advancing Image Retrieval with Few-Shot Learning and Relevance FeedbackCode0
Accurate Open-set Recognition for Memory WorkloadCode0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.